AI Assistant for Insurance Agents at ERGO Hestia
History of Collaboration
ERGO Hestia is a leading insurance company operating on the Polish market, serving millions of individual and business customers. The insurer supports its customers by offering a wide range of products, such as auto, property, and health insurance. The company works with tens of thousands of insurance brokers.
The decision to begin working with Onex Group stemmed from the need to address three key challenges:
- Handling over 60% of the traffic at the broker’s service center related to questions about the General Insurance Terms and Conditions, in order to speed up and streamline the response process.
- Analysis of multi-page documents, including general terms and conditions.
The knowledge base included product information, marketing materials, and highly detailed documents, including the General Terms and Conditions of Insurance, along with their appendices and regulations. - Versioning of the product offering.
The changing product offering resulted in overlapping terms and conditions and coverage scopes for insurance products.
Objectives
What goals have we set?
Key Success KPI: At least 60% of traffic captured by the chatbot
Improving the Efficiency of Insurance Agents
Improving Customer Service Quality
Reducing the time to market for new products
Implementation
How did we respond to the client's needs?
We designed and conducted customized onboarding workshops tailored to the law firm’s expectations. The workshops were designed to address specific challenges related to using Copilot that were reported by Sobota Jachira employees, such as:
- making it easier to find relevant information in correspondence,
- comparing documents and preparing summaries,
- Copilot errors when editing documents,
- The need to limit Copilot’s so-called “hallucinations” when generating content.
The training sessions were held in two groups, which allowed for an interactive approach and full customization for participants from different departments.
Designing solutions based on real-world business processes
The project began with an analysis of how agents work and how information flows within the organization. The key objective was to create a solution that would not change the way end users work, but would naturally enhance existing processes.
Therefore, the intelligent AI search engine was integrated into the existing chat interface via a dedicated WebAPI, which significantly reduced the time it took for the organization to adopt the solution and minimized the need for additional user training.
Architecture based on Microsoft Azure
The solution was designed using a PaaS architecture on the client’s Microsoft Azure tenant, which allowed for full control over the data and compliance with ERGO Hestia’s security policies.
RAG (Retrieval-Augmented Generation)
The use of the RAG (Retrieval Augmented Generation) approach helped reduce the risk of generating incorrect information, as the model generated responses based solely on verified source data.
The solution was also tailored to the organization’s security requirements. The authentication and authorization mechanisms were based on Azure Entra ID and Managed Identity, which enabled the secure deployment of the system in a production environment and ensured compliance with applicable security standards.
Result
What have we accomplished?
Following the implementation of an intelligent AI search engine, measurable business results were achieved, which led to a change in the agents’ work model and the way inquiries are handled within the organization:
- 68% of the traffic received regarding the General Insurance Terms and Conditions
- ~ 90% of conversations with no reported issues
- 20,000 users can use the solution
In practice, the traffic acquisition rate resulted in a significant reduction in the workload on support teams and the ability to scale services without increasing headcount. At the same time, the high quality of responses was the result of using the RAG architecture and a multi-stage response quality testing process, which allowed us to verify the accuracy of responses and their compliance with documentation.
An additional business benefit was the reduction in operating costs and the ability to roll out new products more quickly, since product information was automatically available to agents once the source documents were updated.
Sample questions and answers:
- “How often should a customer have their electrical system inspected?”:
The customer must inspect the technical condition of the electrical installation every 5 years. The inspection should cover the operational condition of connections, accessories, safety devices, and electrical shock protection measures, as well as the insulation resistance of conductors and the grounding of the installation and equipment. The inspection must be performed by individuals who possess the qualifications required to supervise the operation of equipment, installations, and power grids. - “What category does a lawn sprinkler system and solar-powered lights fall under?”
A lawn sprinkler system and solar-powered lights are considered part of garden architecture. Garden architecture includes, among other things, irrigation systems and garden lights, which are considered garden fixtures as defined in the General Terms and Conditions
Artificial intelligence now accounts for as much as 68 percent of the traffic related to general insurance terms and conditions, ensuring ~ 90% of conversations with the bot had no reported issues. However, what pleases us most is that our insurance agents and brokers have received tangible support, which has significantly improved our customer service process.
Paweł Czaja
Deputy Director of Customer Service, ERGO Hestia